IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

  • Upload
    cseij

  • View
    222

  • Download
    0

Embed Size (px)

Citation preview

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    1/13

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    2/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    2

    methods apply different threshold values to different regions of the image. The value is

    determined by the neighborhood of the pixel to which the thresholding is being applied [5].

    The binarization techniques for grayscale documents can be grouped into two broad categories:

    global thresholding binarization and local thresholding binarization [6]. Global methods find a

    single threshold value for the whole document. Then each pixel is assigned to page foreground or

    background based on its gray value comparing with the threshold value. Global methods are veryfast and they give good results for typical scanned documents. For many years, the binarization of

    a grayscale document was based on the global thresholding statistical algorithms. These statistical

    methods, which can be considered as clustering approaches, are inappropriate for complex

    documents, and for degraded documents. If the illumination over the document is not uniformglobal binarization methods tend to produce marginal noise along the page borders. To overcome

    these complexities, local thresholding techniques have been proposed for document binarization.

    These techniques estimate a different threshold for each pixel according to the grayscale

    information of the neighboring pixels. The techniques of Bernsen, Chow and Kaneko, Eikvil,

    Mardia and Hainsworth, Niblack [7], Yanowitz and Bruckstein [8], and TR Singh belong to thiscategory. The hybrid techniques: L.O’Gorman and Liu, which combine information of global and

    local thresholds belong to another category.In this paper we focus on the binarization of grayscale

    documents using local thresholding technique, because in most cases color documents can beconverted to grayscale without losing much information as far as distinction between page

    foreground and background is concerned.

    2. THRESHOLDING TECHNIQUES 

    Threshold technique is one of the important techniques in image segmentation. This technique

    can be expressed as:

    T=T[x, y, p(x, y), f(x, y]

    Where T is the threshold value. x, y are the coordinates of the threshold value point.p(x,y) ,f(x,y)

    are points the gray level image pixels [9].Threshold image g(x,y) can be define:

    g(x,y)=

    Thresholding techniques are classified as bellow

    Figure 1. Thresholding Techniques

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    3/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    3

    Thresholding is classified into two Global Thresholding and Local Thresholding, Global

    thresholding is dived into Traditional,Iterative,Multistage which is difined as a Figure 1.

    2.1 Global Thresholding

    Global (single) thresholding method is used when there the intensity distribution between theobjects of foreground and background are very distinct. When the differences between

    foreground and background objects are very distinct, a single value of threshold can simply be

    used to differentiate both objects apart. Thus, in this type of thresholding, the value of threshold T

    depends solely on the property of the pixel and the grey level value of the image. Some most

    common used global thresholding methods are Otsu method, entropy based thresholding, etc.

    Otsu’salgorithm is a popular global thresholding technique. Moreover, there are many popular

    thresholding techniques such as Kittler and Illingworth, Kapur , Tsai , Huang , Yen and et al [9].

    2.1.1 Traditional Thresholding (Otsu’s Method)

    In image processing, segmentation is often the first step to pre-process images to extract objects

    of interest for further analysis. Segmentation techniques can be generally categorized into two

    frameworks, edge-based and region based approaches. As a segmentation technique, Otsu’s

    method is widely used in pattern recognition, document binarization, and computer vision. In

    many cases Otsu’s method is used as a pre-processing technique to segment an image for further

    processing such as feature analysis and quantification. Otsu’s method searches for a threshold that

    minimizes the intra-class variances of the segmented image and can achieve good results when

    the histogram of the original image has two distinct peaks, one belongs to the background, and

    the other belongs to the foreground or the signal. The Otsu’s threshold is found by searching

    across the whole range of the pixel values of the image until the intra-class variances reach their

    minimum. As it is defined, the threshold determined by Otsu’s method is more profoundly

    determined by the class that has the larger variance, be it the background or the foreground. As

    such, Otsu’s method may create suboptimal results when the histogram of the image has morethan two peaks or if one of the classes has a large variance

    2.1.2 Iterative Thresholding(A New Iterative Triclass Thresholding Technique)

    A new iterative method that is based on Otsu’s method but differs from the standard application

    of the method in an important way. At the first iteration, we apply Otsu’s method on an image to

    obtain the Otsu’s threshold and the means of two classes separated by the threshold as the

    standard application does. Then, instead of classifying the image into two classes separated by the

    Otsu’s threshold, our method separates the image into three classes based on the two class means

    derived. The three classes are defined as the foreground with pixel values are greater than the

    larger mean, the background with pixel values are less than the smaller mean, and more

    importantly, a third class we call the “to-be-determined” (TBD) region with pixel values fall

    between the two class means. Then at the next iteration, the method keeps the previous

    foreground and background regions unchanged and re-applies Otsu’s method on the TBD regiononly to, again, separate it into three classes in the similar manner. When the iteration stops after

    meeting a preset criterion, the last TBD region is then separated into two classes, foreground and

    background, instead of three regions. The final foreground is the logical union of all the

    previously determined foreground regions and the final background is determined similarly. The

    new method is almost parameter free except for the stopping rule for the iterative process and has

    minimal added computational load.

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    4/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    4

    2.1.3 Multistage Thresholding(Quadratic Ratio Technique For Handwritten Character)

    The QIR technique was found superior in thresholding handwriting images where the following

    tight requirements need to be met:

    1. All the details of the handwriting are to be retained2. The papers used may contain strong coloured or patterned background

    3. The handwriting may be written by a wide variety of writing media such as a fountain pen,

    ballpoint pen, or pencil.QIR is a global two stage thresholding technique. The first stage of the

    algorithm divides an image into three sub images: foreground, background, and a fuzzy sub

    image where it is hard to determine whether a pixel actually belongs to the foreground or the

    background (Figure 2). Two important parameters that separate the sub images are A, which

    separates the foreground and the fuzzy sub image, and C, which separate the fuzzy and the

    background sub image. If a pixel’s intensity is less than or equal to A, the pixel belongs to the

    foreground. If a pixel’s intensity is greater than or equal to C, the pixel belongs to the

    background. If a pixel has an intensity value between A and C, it belongs to the fuzzy sub image

    and more information is needed from the image to decide whether it actually belongs to the

    foreground or the background.

    Figure 2. Three Subimages of QIR

    2.2 Local Thresholding

    A threshold T(x,y) is a value such that

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    5/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    5

    Where b(x,y) is the binarized image and I(x,y)∈[0,1] be the intensity of a pixel at location (x,y) of

    the image I. In local adaptive technique, a threshold is calculated for each pixel, based on some

    local statistics such as range, variance, or surface-fitting parameters of the neighborhood pixels. It

    can be approached in different ways such as background subtraction, water flow model, means

    and standard derivation of pixel values, and local image contrast. Some drawbacks of the local

    thresholding techniques are region size dependant, individual image characteristics, and timeconsuming. Therefore, some researchers use a hybrid approach that applies both global and local

    thresholding methods and some use morphological operators. Niblack, and Sauvola and

    Pietaksinen use the local variance technique while Bernsen uses midrange value within the local

    block.[10]

    2.2.1 Niblack’s Techniques

    In this method local threshold value T(x, y)at (x, y) is calculated within a window of size w ×w

    was:

    T(x, y) = m(x, y) + k* δ(x, y)

    Where m(x, y) and δ(x, y)are the local mean and standard deviation of the pixels inside the local

    window and k is a bias. Set as k = 0.5.The local mean m(x, y) and standard deviation δ(x, y)

    adapt the value of the threshold according to the contrast in the local neighborhood of the pixel.

    The bias k controls the level of adaptation varying the threshold value.[11]

    2.2.2 Sauvola’s Technique

    In Sauvola’s technique, the threshold T(x, y) is computed using the mean m(x, y) and standard

    deviation δ(x, y) of the pixel intensities in a w × w window centered around the pixel at (x, y) and

    express as 

    Where R is the maximum value of the standard deviation (R=128 for a grayscale document), and

    k is a parameter which takes positive values in the range [ 0.5] [12].

    2.2.3 Bernsen’s Technique

    This technique, proposed by Bernsen, is a local binarization technique, which uses local contrast

    value to determine local threshold value. The local threshold value for each pixel (x, y) is

    calculated by the relation. 

    T(x,y)=  

    Where Imax and Imin are the maximum and minimum gray level value in a w × w window

    centered at (x, y) respectively [13]. But the threshold assignment is based on local contrast value

    and hence it can be expressed as

    if Imax –Imin >L //if the gray scale image is not uniform

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    6/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    6

    Then

    T(x,y)=  

    ElseT(x, y) = GT //(else threshold value is calculated by global thresholding technique.) 

    Where L is a contrast threshold and GT is a global threshold value.

    2.2.4 Yanowitz and Bruckstein’s Method

    Yanowitz and Bruckstein suggested using the grey-level values at high gradient regions as known

    data to interpolate the threshold surface of image document texture features[14].The key steps of

    this method are:

    1. Smooth the image by average filtering.

    2. Derive the gradient magnitude.

    3. Apply a thinning algorithm to find the object boundary points.

    4. Sample the grey-level in the smoothed image at the boundary points. These are the support

    points for interpolation in step 5.5. Find the threshold surface T(x, y) that is equal to the image values at the support points and

    satisfies the Laplace equation using South well’s successive over relaxation method.

    6. Using the obtained T(x, y), segment the image.

    7. Apply a post-processing method to validate the segmented image

    3. PROPOSED TECHNIQUES 

    3.1 Niblack’s Algorithm

    In local thresholding, the threshold values are spatially varied and determined based on the local

    content of the target image. In comparison with global techniques, local tresholding techniques

    have better performance against noise and error especially when dealing with information neartexts or objects. According to Trier’s survey, Yanowitz Bruckstein’s method and Niblacks

    method are two of the best performing local thresholding methods. Yanowitz-Bruckstein’s

    method is extraordinary complicated and thus requires very Iarge computational power. This

    makes it infeasible and too expensive for real system implementations. On the other hand,Niblacks method is simple and effective. As a result, we decided to focus on Niblack’s method.

    Niblack’s algorithm [15] is a local thresholding method based on the calculation of the local

    mean and of local standard deviation. The threshold is decided by the formula:

    T (x, y) = m( x, y) + k • s(x, y)

    where m(x, y) and s(x, y) are the average of a local area and standard deviation values,

    respectively. The size of the neighborhood should be small enough to preserve local details, but atthe same time large enough to suppress noise. The value of k is used to adjust how much of the

    total print object boundary is taken as a part of the given object.

    3.2 Sauvola’s Technique

    In Sauvola’s technique [16], the threshold TSauvola  is computed using the mean m and standard

    deviation of the pixel intensities in a window centered around the pixel and express

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    7/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    7

    where is the maximum value of the standard deviation (for a grayscale document), and k is a

    parameter which takes positive values in the range [0.5].

    The local mean m and standard deviation s adapt the value of the threshold according to the

    contrast in the local neighborhood of the pixel. When there is high contrast in some region of the

    image, s~ R which results in TSauvola~ m. This is the same result as in Niblack’s method. However,the difference comes in when the contrast in the local neighborhood is quite low. In that case the

    threshold TSauvola goes below the mean value thereby successfully removing the relatively dark

    regions of the background.

    The parameter k controls the value of the threshold in the local window such that the higher thevalue of k, the lower the threshold from the local mean m. A value of k = 0.5 was used by

    Sauvola1 and Sezgin. Badekas et al. experimented with different values and found that k = 0.34

    gives the best result. In general, the algorithm is not very sensitive to the value of k used. Thestatistical constraint gives very good result even for severely degraded document. In order to

    compute the threshold TSauvola, local mean and standard deviation have to be computed for eachpixel its computational complexity is O(n2×w2) in a naive way for an image of size n×n.It means

    that its computational complexity is window size dependent. T.R Singh proposed window size

    independent technique of thersholding using integral sum image as prior process.

    4. RESULT AND DISCUSSION 

    ImagesUsing Niblack

    Tecnique

    Using Sauvola

    Technique

    Image 1

    Image 2

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    8/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    8

    Image 3

    Image 4

    Image 5

    Image 6

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    9/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    9

    Image 7

    Image 8

    Image 9

    Image

    10

    Image11

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    10/13

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    11/13

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    12/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    12

    5. CONCLUSION 

    In This paper describes a locally adaptive thresholding technique that removes background by

    using local mean and standard deviation. Niblack and sauvola thresholding algorithm isimplemented on medical images. In this paper we compare Niblack and Sauvola thresholding

    algorithm .These approaches aiming at removal of background noise. Niblack algorithm reducethe background noice compare to Sauvola algorithm. The performance of proposed algorithms is

    measured using segmentation parameters PSNR, Jaccard Similarity Coefficient.The result of the

    Niblack algorithm is better than the Sauvola algorithm.

    REFERENCES 

    [1] Hui Zhang, Jason E.Fritts, Sally A. Goldman,” Image Segmentation Evaluation: A Survey

    UnsupervisedMethods”,2008.

    [2] Nir Milstein, “Image Segmentation by Adaptive Thresholding”,Spring 1998.

    [3] Sang uk lee, seok yoon chung and Rae hong park, “A Comparative Performance Study of SeveralGlobal Thresholding Techniques for Segmentation”, Computer Vision Graphics And Image

    Processing52, 171-190, 1990

    [4] Graham Leedham, Chen Yan, Kalyan Takru, Joie Hadi Nata Tan and Li Mian, “Comparison of

    Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document

    Images”,Proceedings of the Seventh International Conference on Document Analysis and

    Recognition , 2003.

    [5] Graham Leedham, Chen Yan, Kalyan Takru, Joie Hadi Nata Tan and Li Mian,” Comparison of Some

    Thresholding Algorithms forText/Background Segmentation in Difficult Document Images”,2003.

    [6] O. Imocha Singh, Tejmani Sinam “Local Contrast and Mean based Thresholding Technique in

    Image Binarization” International Journal of Computer Applications (0975 – 8887) Volume 51–

    No.6, August 2012.

    [7] Er.Nirpjeet kaur, Er Rajpreet kaur “A review on various methods of image thresholding” (IJCSE).

    [8] Bülent Sankura, Mehmet Sezginb “Survey over image thresholding techniques and quantitative

    performance evaluation” Journal of Electronic Imaging 13(1), 146–165 (January 2009).

    [9] 1.Priyanka G. Kumbhar, 2 Prof. Sushilkumar N. Holambe,” A Review of Image Thresholding

    Techniques”, International Journal of Advanced Research in Computer Science and Software

    Engineering , Volume 5, Issue 6, June 2015.

    [10] T.Romen Singh1, Sudipta Roy2, O.Imocha Singh3, Tejmani Sinam4, Kh.Manglem Singh, “A New

    Local Adaptive Thresholding Technique in Binarization,” IJCSI International Journal of Computer

    Science Issues, Vol. 8, Issue 6, No 2, November 2011.

    [11] Rukhsar Firdousi, Shaheen Parveen,” Local Thresholding Techniques in Image Binarization”,

    International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3 Issue 3

    March, 2014 Page No. 4062-4065.

    [12] T.Romen Singh, Sudipta Roy, O.Imocha Singh, Tejmani Sinam, Kh.Manglem Singh “A New Local

    Adaptive Thresholding Technique in Binarization” IJCSI International Journal of Computer Science

    Issues, Vol. 8, Issue 6, No 2, November 2011.

    [13] Er.Nirpjeet kaur, Er Rajpreet kaur “A review on various methods of image thresholding” (IJCSE).[14] Graham Leedham, Chen Yan, Kalyan Takru, Joie Hadi Nata Tan and Li Mian “Thresholding

    Algorithms for Text/Background Segmentation in Difficult Document Images” Seventh International

    Conference on Document Analysis and Recognition (ICDAR 2010).

    [15] Niblack (1986), An Introduction to Digital Image Processing, pp. 115 - 116, Prentice Hall.

    [16] J. Sauvola and M. Pietikainen, “Adaptive document image binarization,” Pattern Recognition 33(2),

    pp. 225–236, 2000.

  • 8/19/2019 IMAGE SEGMENTATION BY USING THRESHOLDING TECHNIQUES FOR MEDICAL IMAGES

    13/13

    Computer Science & Engineering: An International Journal (CSEIJ), Vol.6, No.1, February 2016

    13

    AUTHORS 

    S.vaithegi doing M.phil computer science in Gandhigram Rural Institute-Deemed

    University, TamilNadu and done in Master of computer Application in kumarasamy

    Engineering College TamilNadu. Her research area include image processing.

    .